INDEX

Explanations

keywords related to altruistic values and supportive actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.41

-0.40

 fino

-0.39

-0.38

lor

-0.38

it

-0.37

POSITIVE LOGITS

EDEFAULT

1.06

 CURIAM

1.02

 Мексичка

1.01

 مشين

1.01

tonode

0.96

WriteTagHelper

0.94

protoimpl

0.94

:✨

0.94

 defaultstate

0.91

ValueStyle

0.91

Activations Density 0.047%

keywords related to altruistic values and supportive actions

No Comments

No Known Activations